Group items tagged

Abstract: "Game Artificial Intelligence (Game AI) is a subdiscipline of Artificial Intelligence (AI) and Machine Learning (ML) that explores the ways in which AI and ML can augment player experiences in computer games. Storytelling is an integral part of many modern computer games; within games stories create context, motivate the player, and move the action forward. Interactive Narrative is the use of AI to create and manage stories within games, creating the perception that the player is a character in a dynamically unfolding and responsive story. This paper introduces Game AI and focuses on the open research problems of Interactive Narrative."

From the abstract: "Collective Artificial Intelligence (CAI) simulates human intelligence from data contributed by many humans, mined for inter-related patterns. This thesis applies CAI to social role-playing, introducing an end-to-end process for compositing recorded performances from thousands of humans, and simulating open-ended interaction from this data. The CAI process combines crowdsourcing, pattern discovery, and case-based planning. Content creation is crowdsourced by recording role-players online. Browser-based tools allow non-experts to annotate data, organizing content into a hierarchical narrative structure. Patterns discovered from data power a novel system combining plan recognition with case-based planning. The combination of this process and structure produces a new medium, which exploits a massive corpus to realize characters who interact and converse with humans. This medium enables new experiences in videogames, and new classes of training simulations, therapeutic applications, and social robots. .... As a proof of concept, a CAI system has been evaluated by recording over 10,000 performances in The Restaurant Game, automating an AI-controlled waitress who interacts in the world, and converses with a human via text or speech. Quantitative results demonstrate CAI supports significantly open-ended interaction with humans, while focus groups reveal factors for improving engagement."

Her name is Angelina: she runs on a heavy-duty Mac server and she's building some addictive computer games for you. Angelina (a tail-recursive acronym for "A Novel Game-Evolving Labrat I've Named ANGELINA") is a project in evolutionary computing by Michael Cook, a PhD candidate at Imperial College in the UK.

Abstract: "Non-player Characters (NPCs) that accompany the player en- able a single player to participate in team-based experiences, improving immersion and allowing for more complex game- play. In this context, an Artificial Intelligence (AI) teammate should make good combat decisions, supporting the player and optimizing combat resolution. Here we investigate the target selection problem, which consists of picking the op- timal enemy as a target in a modern war game. We look at how the companion's different strategies can influence the outcome of combat, and by analyzing a variety of non-trivial First Person Shooter (FPS) scenarios show that a mathemat- ically simple approach significantly improves over common strategies typically found in games, and can achieve results similar to much more expensive look-up tree approaches. This work has applications in practical game design, show- ing that simple, computationally efficient target selection can make an excellent target selection heuristic"

Abstract: "A number of changes are occurring in the field of computer game development: persistent online games, digital distribution platforms, social and mobile games, and the emer- gence of new business models have pushed game development to put heavier emphasis on the live operation of games. Artificial intelligence has long been an important part of game development practices. The forces of change in the industry present an opportunity for Game AI to have new and profound impact on game development practices. Specifically, Game AI agents should act as "producers" responsible for managing a long-running set of live games, their player communities, and real-world context. We characterize a confluence of four major forces at play in the games industry today, together producing a wealth of data that opens unique research opportunities and challenges for Game AI as producers. We enumerate 12 new research areas spawned by these forces and steps toward how they can be addressed by data-driven Game AI Producers"

"We argue that the development of innovative artificial intelligence (AI) systems plays a crucial role in the exploration of currently unreachable spaces. To aid in exploration, we suggest a practice called AI-based game design, an iterative design process that deeply integrates the affordances of an AI system within the context of game design."

"Abstract-While component reuse is a common concept in software engineering, it does not yet have a strong foothold in Computer Game development, in particular the development of computer-controlled game characters. In this work, we take a modular Statechart-based game AI modelling approach and develop a reuse strategy to enable fast development of new AIs. This is aided through the creation of a standardized interface for Statechart modules in a layered architecture. Reuse is enabled at a high-level through functional groups that encapsulate behaviour. These concepts are solidified with the development of the SkyAI tool. SkyAI enables a developer to build and work with a library of modular components to develop new AIs by composing modules, and then output the resulting product to an existing game. Efficacy is demonstrated by reusing AI components from a tank to quickly make a much different AI for a simple animal."

Abstract: "Abstract Game developers spend a large portion of their time developing and tweaking the articial intelligence in video games. Problems related to productivity in the development of AI have been solved using various modeling techniques in the eld of AI, language design and easier to use editors. Using a domain specic language to assist in describing AI can increase productivity in this area. In addition to this, game developers can be relieved from irrelevant tasks such as worrying about performance, correctness of the implementation, memory management and optimiza- tion data structures and focus on the high level description of the game play. In this thesis, we focus on real-time video games and we investigate the development of a domain-specic language containing the necessary elements to describe and execute strategies to achieve goals in a real-time video game. We develop a domain-specic language to express strategies for computer controlled actors using techniques commonly found in em- bedded domain-specic languages, and in particular embedded domain- specic languages in Haskell. To demonstrate this language we have developed a prototype of a real-time strategy game that uses strategies implemented using the domain-specic language developed in this thesis"

"As research for a Ph.D. thesis, we propose to show that a layered Statechart-based AI is a suitable formalism for Game AI, enabling the use of model-driven development techniques such as reuse and high-level analysis including model-checking. The fundamentally modular nature of this approach leads naturally to reuse as a fundamental component of the design process. Supported by a clearly defined formalism, useful behavioural analyses become possible, such as testing reactions to various inputs at design time. We also explore transformations at the modelling level to enable procedural generation, allowing rapid deployment of varying AIs. Additionally, such a model allows for the generation of efficient code that can be directly inserted into games. Tool support for reuse, generation, and analysis will be developed, then employed in creating an industrial scale AI, proving that this formalism is appropriate for industrial use."

Abstract: "This paper explores the use of modern sensor technologies for physical interaction on educati onal games and interactive spaces. More specifically the thesis studies the potential effect of motion capture and wearable body sensors on educational interactive games, on two aspects: i) on the involvement of human body and motion in the process of lear ning, and recall of knowledge (embodied learning), ii) on assisting the development of basic social emotional competencies, through the enhanced social affordances of embodied games. The paper presents a prototype of an educational game developed using a m otion capture controller and two bio feedback sensors, proposing a generic architecture for multi sensor interactive spaces. Finally the paper provides a review of previously studied modalities for emotion recognition, and examines their application on gam e mechanics and AI game agents."

From the abstract: "Here we demonstrate for the first time the iterative development of agent behaviour for a real-time strategy game (here StarCraft) utilising Behaviour Oriented Design (BOD) [7]. BOD provides focus on the robust creation and easy adjustment of modular and hierarchical cognitive agents. We demonstrate BOD's usage in creating an AI capable of playing the StarCraft character the Zerg hive mind, and document its performance against a variety of opponent AI systems. In describing our tool-driven development process, we also describe the new Abode IDE, provide a brief literature review situating BOD in the AI game literature, and propose possible future work."

"Two-Population Novelty Search for Generating Game Content"

Proposal to allow "experiment with AI bots," considering gaming competitions and Blizzard online games

From the abstract: "Traditionally, the tasks associated with game AI revolved around non player character (NPC) behavior at dierent levels of control, varying from navigation and pathnding to decision making. Commercial-standard games developed over the last 15 years and current game productions, however, suggest that the traditional challenges of game AI have been well addressed via the use of sophisticated AI approaches, not necessarily following or inspired by advances in academic practices. The marginal penetration of traditional academic game AI methods in industrial productions has been mainly due to the lack of constructive communication between academia and industry in the early days of academic game AI, and the inability of academic game AI to propose methods that would signicantly advance existing development processes or provide scalable solutions to real world problems. Recently, however, there has been a shift of research focus as the current plethora of AI uses in games is breaking the non-player character AI tradition. A number of those alternative AI uses have already shown a signicant potential for the design of better games. This paper presents four key game AI research areas that are currently reshaping the research roadmap in the game AI eld and evidently put the game AI term under a new perspective. These game AI agship research areas include the computational modeling of player experience, the procedural generation of content, the mining of player data on massive-scale and the alternative AI research foci for enhancing NPC capabilities."